应用科技
應用科技
응용과기
Applied Science and Technology
2015年
5期
34-37,82
,共5页
无人机%人工标志%视觉导航%连续自适应的均值漂移算法
無人機%人工標誌%視覺導航%連續自適應的均值漂移算法
무인궤%인공표지%시각도항%련속자괄응적균치표이산법
UAV%artificial mark%vision navigation%continuously adaptive mean-shift ( CamShift)
为了实现无人机长时间的精确定位,提出了一种新的视觉导航方法. 无人机机载摄像头实时采集无人机相对人工标志物的图像,采用基于CamShift的特征目标跟踪算法,实时识别人工标志,并计算无人机相对标志物的质心位置与图像中心的偏差以及方向角偏差,无人机根据偏差数据生成飞行控制律,调整无人机姿态,实现对无人机的引导. 实验验证了该算法的正确性和有效性.
為瞭實現無人機長時間的精確定位,提齣瞭一種新的視覺導航方法. 無人機機載攝像頭實時採集無人機相對人工標誌物的圖像,採用基于CamShift的特徵目標跟蹤算法,實時識彆人工標誌,併計算無人機相對標誌物的質心位置與圖像中心的偏差以及方嚮角偏差,無人機根據偏差數據生成飛行控製律,調整無人機姿態,實現對無人機的引導. 實驗驗證瞭該算法的正確性和有效性.
위료실현무인궤장시간적정학정위,제출료일충신적시각도항방법. 무인궤궤재섭상두실시채집무인궤상대인공표지물적도상,채용기우CamShift적특정목표근종산법,실시식별인공표지,병계산무인궤상대표지물적질심위치여도상중심적편차이급방향각편차,무인궤근거편차수거생성비행공제률,조정무인궤자태,실현대무인궤적인도. 실험험증료해산법적정학성화유효성.
An approach of vision navigation of an unmanned aerial vehicle( UAV) with artificial marks is proposed in this paper. The image of the UAV relative to the artificial mark is gained by the airborne camera in real time. Then the artificial mark is recognized by the object tracking algorithm based on continuously adaptive mean-shift ( CamShift) . Moreover, the deviation between centroid position of the UAV relative to the artificial mark and image center and the angle deviation of the direction are computed. At the same time, the flight control law of UAV is generated according to the deviated data and the UAV attitude can be adjusted by the flight control law in order to realize the guidance of the UAV. Finally, the correctness and effectiveness of the proposed algorithm are verified through some experiments.
